Tuesday, 21 July 2026 Sign in

From OpenAI to Open LLMs with Messages API on Hugging Face

Hugging Face Blog 8 February 2024, 00:00

Hugging Face released a Messages API in Text Generation Inference version 1.4.0 that makes open-source language models compatible with OpenAI's Chat Completion API, allowing users to swap between OpenAI and open models using existing client libraries. The API works with OpenAI's Python and JavaScript clients as well as third-party frameworks like LangChain and LlamaIndex, requiring only a change in the endpoint URL and API key. The Messages API does not currently support function calling and only works with models that have a chat_template defined in their tokenizer configuration.

Read the full story at Hugging Face Blog

Hugging Face

Every AI story that matters,
in your inbox by 8am.

TLDRocket reads 60+ sources, removes duplicate coverage, and summarises the day in two minutes. Free, no spam, unsubscribe anytime.

TLDRocket 21 July 2026

The open-weight AI model market hit an inflection point today as Alibaba and Kimi released trillion-parameter competitors that challenge the closed-model orthodoxy—just as Washington moved to restrict them. Alibaba's Qwen 3.8 Max (2.4 trillion parameters) and Kimi K3 (2.8T) are going open-weight, with K3 ranking first on Frontend Web App Arena and fourth on agentic benchmarks, signaling that scale and transparency can coexist. The timing matters: while U.S. policymakers weigh layered restrictions on Chinese open models, technical experts are pushing back hard, arguing that closed gardens actually hurt security and competition more than they help. The real fragmentation risk isn't technical—it's regulatory.

Read the full briefing →

From OpenAI to Open LLMs with Messages API on Hugging Face

Related stories

Every AI story that matters, in your inbox by 8am.

Every AI story that matters,
in your inbox by 8am.